© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111515
    Prev
    Next
    INDEX
    Explanations

    -ation, -ate, -ated, -ates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utilisons
    1.23
    н
    1.21
    n
    1.19
    lą
    1.08
    läuft
    1.08
    ем
    1.07
     està
    1.07
    intérieur
    1.04
     لوبوي
    1.03
    ný
    1.01
    POSITIVE LOGITS
    '
    1.79
     of
    1.60
    ع
    1.41
    ول
    1.31
    ح
    1.23
     to
    1.17
     for
    1.09
     that
    1.09
     is
    1.08
    س
    1.06
    Activations Density 0.003%

    No Known Activations